> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ai-coustics.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Quail Multi Speaker

> Multi-speaker speech enhancement for speech-to-text and voice agents.

**Quail Multi Speaker** processes audio for machine listening, including speech-to-text (STT) and voice agents. The multi-speaker models target noise and reverberation while retaining speech from multiple participants.

Use Quail Multi Speaker when every speaker matters, such as a meeting transcription or speakerphone application. If your application should follow one primary speaker and suppress competing speech, evaluate [Quail Voice Focus](/models/voice-focus/quail-voice-focus).

## Choose a variant

| Input and task | Candidate model IDs |
| - | - |
| 16 kHz speech for STT | `quail-ms-l-16khz`, `quail-ms-s-16khz` |
| 8 kHz telephony speech | `quail-ms-l-8khz`, `quail-ms-s-8khz` |

The small and large variants give you alternatives to compare for quality and resource use. Measure both with your recordings, STT provider and target hardware. The [model reference](/reference/sdk/models#quail-multi-speaker) lists release-specific rates and block sizes.

## Evaluate the result

Compare the original and enhanced audio using the same STT model, transcription settings and labeled recordings. Track word error rate (WER), insertions, deletions and task completion. Enhancement does not guarantee an improvement for every recording or STT provider.

<Note>
  Quail Multi Speaker is optimized for machine listening. Some noise or reverberation can remain, and the output may differ from what a human listener considers natural. Use [Rook Multi Speaker](/models/perceptual-speech-enhancement/rook-multi-speaker) when human listening is the primary goal.
</Note>

Follow the [STT tuning guide](/models/speech-enhancement/speech-enhancement-for-voice-ai-systems) and [SDK quickstart](/models/get-started/sdk-quickstart) to evaluate a complete integration.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.